Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers
Kanban boards, databases, and pages that Claude, Cursor, and any AI agent can read and write via MCP — alongside you.
Seamlessly integrate Anki with AI assistants through the Model Context Protocol
A Model Context Protocol (MCP) server that provides conversational interface for the exploration and analysis of RDF (Turtle) based Knowledge Graph in Local File mode or SPARQL Endpoint mode.
* Easily manage all connected MCP servers through an intuitive web interface (optional, requires enabling). * Enable or disable individual tools, and override names/descriptions via the Web UI.
90+ tools for macOS automation: - 📱 - Send/read iMessages, list chats, send file attachments, search/get/create/update contacts - 📝 - Create, list, search, update, show, move, complete, and delete...
- 让 AI 像 Claude Code 一样进行完整的 Web 开发、数据处理和代码执行
This directory contains a Model Context Protocol (MCP) server designed to allow AI agents to interact with Jupyter Notebook (.ipynb) files. It was created to overcome a limitation with Cursor.
Once you get the mcp server running you need to initialize the rules (custom-modes) for the agent you are using
A Model Context Protocol (MCP) server that gives AI assistants the ability to render, export, and analyze 3D models using OpenSCAD. Built with FastMCP for Python.
Similar to Firecrawl's API but self-hosted and free. Perfect for integrating web scraping into your AI workflows with OpenAI Agents SDK, Cursor, Claude Code, and other MCP-compatible tools.
A Node.js Model Context Protocol (MCP) server for searching and downloading academic papers from multiple sources, including arXiv, Web of Science, PubMed, Google Scholar, Sci-Hub, ScienceDirect,...
This MCP server allows the use of natural language to execute any CLI for Microsoft 365 commands. It may handle complex prompts that will be executed as a chain of CLI for Microsoft 365 commands that...
Agent Skills
"The parts that separate a fun demo from a stable toolchain: memory, compression, verification, routing, proactive jobs."
把散落在各个 Agent 里的 Skills，收进一个本地优先的工作台。 一个 Rust 单二进制工具，用来扫描、审计、启停和部署 Codex、Claude Code、Gemini CLI 等 AI Agent 实际读取的 Skill。
一行命令,让你的 AI 助手学会查文献、写综述、跑回归、管引文、写基金—— 科研龙虾 (Research-Claw) 的内置技能库,同时兼容 40+ 主流 Agent 框架。
基于 xiaohongshu-mcp 的 Agent Skills 集合，为小红书提供完整的自动化操作能力。兼容 Agent Skills 开放标准，支持 OpenClaw、Claude Code 等平台。
MoChat: Reconnecting the World through AI Agents
basecamp is the official command-line interface for Basecamp. Manage projects, todos, messages, and more from your terminal or through AI agents.
"The LLM has no 'hallucination problem'. Hallucination is all LLMs do. They are dream machines."
A comprehensive Claude Code skill for designing professional, polished mobile app interfaces that follow proven design principles from top-tier apps like Airbnb, Duolingo, Spotify, Revolut, and...
一个 Claude Code / Codex 技能（Skill），用于将 macOS 微信桌面端的本地聊天记录全量导出为明文 SQLite 数据库。
Evaluate quality. Find the weakest link. Fix it. Prove it worked. Repeat.
Public skills for working with Grafana, Prometheus, Loki, Tempo, Pyroscope, k6, and the broader LGTM observability stack.
本仓库是一套面向 的白盒代码安全审计 Skill 集合，覆盖「路由枚举 → 鉴权建模 → 数据流追踪 → 分类漏洞审计 → 证据一致性校验 → 报告汇总」全流程；在 Cursor 等环境中以 的方式落地。